A Java API for Natural Language Generation that handles morphological realization, text generation, and basic aggregation.
SimpleNLG is a Java API for Natural Language Generation that serves as a realization engine, converting syntactic structures into coherent English text. It handles morphological realization, text generation, and basic aggregation, making it suitable for various NLG applications. The project originated from academic research at the University of Aberdeen and has been adopted in both academic and commercial settings.
Researchers, developers, and organizations working on Natural Language Generation projects who need a practical, Java-based tool for generating English text from syntactic inputs.
Developers choose SimpleNLG for its simplicity and effectiveness compared to more complex NLG tools, offering adequate grammatical coverage for many tasks without excessive overhead. Its integration with the NIH Specialist Lexicon and support for multiple language adaptations (French, Italian, Spanish, etc.) add to its versatility.
Java API for Natural Language Generation. Originally developed by Ehud Reiter at the University of Aberdeen’s Department of Computing Science and co-founder of Arria NLG. This git repo is the official SimpleNLG version.
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
SimpleNLG is a pure Java API with Maven support, making it easy to integrate into existing Java-based NLP pipelines and projects, as shown in the README's quick start guide.
Developed at the University of Aberdeen and used by Arria NLG, it has a proven track record in both research and industry applications, ensuring reliability for practical use.
Supports the NIH Specialist Lexicon for improved morphological accuracy, enhancing text quality beyond the default system, as noted in the features section.
Designed as a lightweight realization engine, it avoids the complexity of comprehensive tools like KPML, making it accessible for many NLG tasks without excessive setup.
The README explicitly states that grammatical coverage is limited compared to tools like KPML and FUF/SURGE, which may not suffice for advanced or nuanced NLG requirements.
Currently offers only simple aggregation, with future plans indicating a lack of advanced features in text planning, limiting its use for complex discourse generation.
The official version only generates English text; support for other languages relies on community adaptations that may vary in quality, maintenance, and documentation.